• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.733-735
• /
• 2018

최근의 차량 주차관리 시설, 출입통제가 필요한 장소 그리고 도로 방범카메라를 통한 단속 등 다양한 곳에서 차량 번호판 자동 인식 기술들이 활용되고 있다. 하지만 현재 사용되고 있는 LPR(License Plate Recognition) 시스템에는 많은 장비와 비용이 들어간다는 큰 단점이 존재한다. 본 논문에서는 하나의 컴퓨터와 최소의 카메라를 가지고 할 수 있는 기계학습을 통한 영상처리를 제안하려 한다. 먼저 딥러닝 프레임워크 중 하나인 YOLO(You Only Look Once) [4]를 활용하여 자동차의 번호판 부분의 영역을 검출하고 Grayscale를 통해 햇빛 또는 조명 등의 영향을 감소시켜 번호판의 특징을 보존시킨다. 전처리 작업이 끝난 후 번호판에서 숫자를 인식 하는 부분에서는 k-NN(k-Nearest Neighbor) 알고리즘을 사용하였으며 한글 문자 인식부분은 Template Matching을 이용하였다. 제안한 알고리즘을 사용하여 기존 LPR 시스템에서 획득한 차량이미지를 대상으로 시뮬레이션 한 결과 좋은 결과를 얻을 수 있어 향후 연구 방향의 시스템 확장성의 가능성을 발견할 수 있었다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.76-85
• /
• 2019

We introduce a vision-based object detection method for real-time video surveillance system in low-end edge computing environments. Recently, the accuracy of object detection has been improved due to the performance of approaches based on deep learning algorithm such as Region Convolutional Neural Network(R-CNN) which has two stage for inferencing. On the other hand, one stage detection algorithms such as single-shot detection (SSD) and you only look once (YOLO) have been developed at the expense of some accuracy and can be used for real-time systems. However, high-performance hardware such as General-Purpose computing on Graphics Processing Unit(GPGPU) is required to still achieve excellent object detection performance and speed. To address hardware requirement that is burdensome to low-end edge computing environments, We propose sub-frame analysis method for the object detection. In specific, We divide a whole image frame into smaller ones then inference them on Convolutional Neural Network (CNN) based image detection network, which is much faster than conventional network designed forfull frame image. We reduced its computationalrequirementsignificantly without losing throughput and object detection accuracy with the proposed method.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.5
• /
• pp.555-562
• /
• 2021

In this paper, we propose a sorting method for extracting accurate license plate information, which is currently used in Korea, after detecting objects using YOLO. We propose sorting methods for the five types of vehicle license plates managed by the Ministry of Land, Infrastructure and Transport by classifying the plates with the number of lines, Korean characters, and numbers. The results of experiments with 5 license plates show that the proposed algorithm identifies all license plate types and information by focusing on the object with high reliability score in the result label file presented by YOLO and deleting unnecessary object information. The proposed method will be applicable to all systems that recognize license plates.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.317-318
• /
• 2019

가상/증강현실로 대표되는 공간정보 기반 실감형 콘텐츠에 대한 관심이 증대되면서 객체인식 등의 지능형 공간인지 기술에 대한 연구가 활발히 진행되고 있다. 특히 HMD등의 영상 시각화 장치의 발달 및 5G 통신기술의 출현으로 인해 실시간 대용량 영상정보의 송, 수신 및 가시화 처리 기술의 기반이 구축됨에 따라, $360^{\circ}$ 스트리밍 영상정보 처리와 같은 고자유도 콘텐츠를 위한 관련 연구의 필요성이 증대되고 있다. 하지만 지능형 영상정보 처리의 대표적 연구인 딥 러닝(Deep Learning) 기반 객체 인식 기술의 경우 대부분 일반적인 평면 영상(Planar Image)에 대한 처리를 다루고 있고, 파노라마 영상(Panorama Image) 특히, $360^{\circ}$ 스트리밍 영상 처리를 위한 연구는 미비한 상황이다. 본 논문에서는 딥 러닝을 이용하여 $360^{\circ}$ 스트리밍 영상에서의 객체인식 연구 방법에 대해 서술한다. 이를 위해 $360^{\circ}$ 카메라 영상에서 딥 러닝을 위한 학습 데이터를 획득하고, 실시간 객체 인식이 가능한 YOLO(You Only Look Once)기법을 이용하여 학습을 한다. 실험 결과에서는 학습 데이터를 이용하여 $360^{\circ}$영상에서 객체 인식 결과와, 학습 횟수에 따른 객체 인식에 대한 결과를 보여준다.

• Journal of the Korea Safety Management & Science
• /
• v.23 no.1
• /
• pp.9-15
• /
• 2021

The leading source of occupational fatalities is a portable ladder in Korea because it is widely used in industry as work platform. In order to reduce victims, it is necessary to establish preventive measures for the accidents caused by portable ladder. Therefore, this study statistically analyzed injury death by portable ladder for recent 10 years to investigate the accident characteristics. Next, to monitor wearing of safety helmet in real-time while working on a portable ladder, this study developed an object detection model based on the You Only Look Once(YOLO) architecture, which can accurately detect objects within a reasonable time. The model was trained on 6,023 images with/without ladders and safety helmets. The performance of the proposed detection model was 0.795 for F1 score and 0.843 for mean average precision. In addition, the proposed model processed at least 25 frames per second which make the model suitable for real-time application.

• Korean Journal of Materials Research
• /
• v.31 no.12
• /
• pp.719-726
• /
• 2021

Through the process of chemical vapor deposition, Tungsten Hexafluoride (WF₆) is widely used by the semiconductor industry to form tungsten films. Tungsten Hexafluoride (WF₆) is produced through manufacturing processes such as pulverization, wet smelting, calcination and reduction of tungsten ores. The manufacturing process of Tungsten Hexafluoride (WF₆) is required thorough quality control to improve productivity. In this paper, a real-time detection system for oxidation defects that occur in the manufacturing process of Tungsten Hexafluoride (WF₆) is proposed. The proposed system is implemented by applying YOLOv5 based on Convolutional Neural Network (CNN); it is expected to enable more stable management than existing management, which relies on skilled workers. The implementation method of the proposed system and the results of performance comparison are presented to prove the feasibility of the method for improving the efficiency of the WF₆ manufacturing process in this paper. The proposed system applying YOLOv5s, which is the most suitable material in the actual production environment, demonstrates high accuracy (mAP@0.5 99.4 %) and real-time detection speed (FPS 46).

• Smart Structures and Systems
• /
• v.28 no.6
• /
• pp.811-825
• /
• 2021

High-voltage isolating switches play a paramount role in ensuring the safety of power supply systems. However, their exposure to outdoor environmental conditions may cause serious physical defects, which may result in great risk to power supply systems and society. Image processing-based methods have been used for anomaly detection. However, their accuracy is affected by numerous uncertainties due to manually extracted features, which makes the anomaly detection of isolating switches still challenging. In this paper, a vision-based anomaly detection method for isolating switches, which uses the rotational angle of the switch system for more accurate and direct anomaly detection with the help of deep learning (DL) and image processing methods (Single Shot Multibox Detector (SSD), improved frame differencing method, and Hough transform), is proposed. The SSD is a deep learning method for object classification and localization. In addition, an improved frame differencing method is introduced for better feature extraction and a hough transform method is adopted for rotational angle calculation. A number of experiments are conducted for anomaly detection of single and multiple switches using video frames. The results of the experiments demonstrate that the SSD outperforms the You-Only-Look-Once network. The effectiveness and robustness of the proposed method have been proven under various conditions, such as different illumination and camera locations using 96 videos from the experiments.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.6_1
• /
• pp.927-939
• /
• 2022

This study was conducted to develop a Web-GIS based monitoring module of smart city that can effectively respond, manage and improve situation in all stages of illegal dumping management on a city scale. First, five technologies were set for the core technical elements of the module configuration. Five core technical elements are as follows; video screening technology based on motion vector analysis, human behavior detection based on intelligent video analytics technology, mobile app for receiving civil complaints about illegal dumping, illegal dumping risk model and street cleanliness map, Web-GIS based situation monitoring technology. The development contents and results for each set of core technical elements were evaluated. Finally, a Web-GIS based 'illegal dumping monitoring module' was proposed. It is possible to collect and analyze city data at the local government level through operating the proposed module. Based on this, it is able to effectively detect illegal dumpers at relatively low cost and identify the tendency of illegal dumping by systematically managing habitual occurrence areas. In the future, it is expected to be developed in the form of an add-on module of the smart city integration platform operated by local governments to ensure interoperability and scalability.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.7-13
• /
• 2021

This paper presents an vulnerable road user (VRU) classification and tracking algorithm using vision and LiDAR sensor fusion method for urban autonomous driving. The classification and tracking for vulnerable road users such as pedestrian, bicycle, and motorcycle are essential for autonomous driving in complex urban environments. In this paper, a real-time object image detection algorithm called Yolo and object tracking algorithm from LiDAR point cloud are fused in the high level. The proposed algorithm consists of four parts. First, the object bounding boxes on the pixel coordinate, which is obtained from YOLO, are transformed into the local coordinate of subject vehicle using the homography matrix. Second, a LiDAR point cloud is clustered based on Euclidean distance and the clusters are associated using GNN. In addition, the states of clusters including position, heading angle, velocity and acceleration information are estimated using geometric model free approach (GMFA) in real-time. Finally, the each LiDAR track is matched with a vision track using angle information of transformed vision track and assigned a classification id. The proposed fusion algorithm is evaluated via real vehicle test in the urban environment.

• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.98-102
• /
• 2023

This paper presents a study on how augmenting semi-synthetic image data improves the performance of human detection algorithms. In the field of object detection, securing a high-quality data set plays the most important role in training deep learning algorithms. Recently, the acquisition of real image data has become time consuming and expensive; therefore, research using synthesized data has been conducted. Synthetic data haves the advantage of being able to generate a vast amount of data and accurately label it. However, the utility of synthetic data in human detection has not yet been demonstrated. Therefore, we use You Only Look Once (YOLO), the object detection algorithm most commonly used, to experimentally analyze the effect of synthetic data augmentation on human detection performance. As a result of training YOLO using the Penn-Fudan dataset, it was shown that the YOLO network model trained on a dataset augmented with synthetic data provided high-performance results in terms of the Precision-Recall Curve and F1-Confidence Curve.